From the course: Responsible AI on AWS: Bedrock Guardrails, Amazon Q Security, and SageMaker Clarify
Unlock this course with a free trial
Join today to access over 25,000 courses taught by industry experts.
Visualizing Bedrock API calls
From the course: Responsible AI on AWS: Bedrock Guardrails, Amazon Q Security, and SageMaker Clarify
Visualizing Bedrock API calls
(computer key clacks) - [Instructor] Here we have the CloudTrail system, which is a great way to audit from a security's perspective what's happening on your system. But only text alone is not as descriptive sometimes for maybe a security event or you want to build a dashboard. And so we need to get some actual data visualization as well. So, first up, let's do a query for bedrock calls here, and we'll type in bedrock calls. And what's nice about this is we can leverage the English language to generate a SQL query, and that's going to build a SQL query that will look at the event store and tell us all of the bedrock calls. Of course we can tweak this and change it around a little bit, but in general this is a pretty good start. We have bedrock, bedrock agent and bedrock runtime. These are the event sources that we care about. And then if we look at the visualization here, well, first we can look at the command output and we can run it. And this will give us a overview of the total…
Contents
-
-
Course introduction1m 29s
-
(Locked)
AI security architecture4m 19s
-
(Locked)
AI auth patterns4m 1s
-
(Locked)
Complete AI security3m 49s
-
(Locked)
AI monitoring and logging3m 51s
-
(Locked)
AWS Rust compilation3m 49s
-
(Locked)
Monitoring Bedrock calls3m 46s
-
(Locked)
Visualizing Bedrock API calls2m 51s
-
-
-
-
-